Improving Auto-Augment via Augmentation-Wise Weight Sharing

09/30/2020
by   Keyu Tian, et al.
6

The recent progress on automatically searching augmentation policies has boosted the performance substantially for various tasks. A key component of automatic argumentation search is the evaluation process for a particular augmentation policy, which is utilized to return reward and usually runs thousands of times. A plain evaluation process, which includes full model training and validation, would be time-consuming. To achieve efficiency, many choose to sacrifice evaluation reliability for speed. In this paper, we dive into the dynamics of augmented training of the model. This inspires us to design a powerful and efficient proxy task based on the Augmentation-Wise Weight Sharing (AWS) to form a fast yet accurate evaluation process in an elegant way. Comprehensive analysis verifies the superiority of this approach in terms of effectiveness and efficiency. The augmentation policies found by our method achieve the best accuracy compared with existing auto-augmentation search methods. On CIFAR-10, we achieve a top-1 error rate of 1.24 currently the best performing single model without extra training data. On ImageNet, we get a top-1 error rate of 20.36 3.34

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/24/2019

Adversarial AutoAugment

Data augmentation (DA) has been widely utilized to improve generalizatio...
research
05/17/2019

Online Hyper-parameter Learning for Auto-Augmentation Strategy

Data augmentation is critical to the success of modern deep learning tec...
research
09/30/2021

DAAS: Differentiable Architecture and Augmentation Policy Search

Neural architecture search (NAS) has been an active direction of automat...
research
10/19/2022

G-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR

Data augmentation is a ubiquitous technique used to provide robustness t...
research
05/01/2019

Fast AutoAugment

Data augmentation is an indispensable technique to improve generalizatio...
research
02/25/2020

PointAugment: an Auto-Augmentation Framework for Point Cloud Classification

We present PointAugment, a new auto-augmentation framework that automati...
research
05/27/2019

LAW: Learning to Auto Weight

Example weighting algorithm is an effective solution to the training bia...

Please sign up or login with your details

Forgot password? Click here to reset